Causal

Member of Technical Staff — Security Engineering

San Francisco. Posted 3 months ago

The role

You will design and operate the security posture across the entire engineering stack. This includes securing research environments, proprietary model weights, software infrastructure, and customer integrations.

What you will do

  • Architect secure network perimeters, private data transmission channels, and isolated storage environments.
  • Implement access controls and customer-managed encryption across petabyte-scale data stores.
  • Design zero-trust boundaries, encrypted storage, and secure execution environments to protect model weights.
  • Secure data ingestion pipelines against tampering and data poisoning.
  • Threat-model and defend against AI-specific vulnerabilities using output guardrails and privacy-preserving techniques.
  • Own enterprise identity federation and machine-to-machine authentication.
  • Implement immutable audit logging, cryptographic erasure, and compliance controls.
  • Build automated security testing, threat detection, and vulnerability scanning into deployment workflows, orchestrators, and APIs.

Required qualifications

  • Proven track record building and securing production systems in cloud environments (AWS, GCP, or Azure) or large-scale distributed systems.
  • Practical mastery of IAM, network perimeters, KMS/encryption, and secrets management.
  • Hands-on experience with Linux systems, networking, container security (Docker, Kubernetes), and Infrastructure-as-Code (Terraform or Pulumi).
  • Proficiency in languages like Python, Go, or Rust.
  • Practical grasp of the security challenges unique to ML platforms including protecting model weights, securing distributed training pipelines, data lineage/poisoning, and AI-specific threat vectors.
  • Ability to conduct architectural security reviews and dig into complex distributed systems.
  • Ability to take deliverables autonomously from initial threat modeling through execution, deployment, and monitoring.

About the company

Causal is building a Large Physics foundation Model (LPM) to achieve general causal intelligence. The founding team has built and deployed AI in robotics, drug discovery, and particle physics at institutions like DeepMind, Waymo, Cruise, Insitro, Nabla Bio, and CERN.